© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156906
    Prev
    Next
    INDEX
    Explanations

    order

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    獼
    0.39
     Imam
    0.38
    parsedBlock
    0.37
     override
    0.35
     qty
    0.35
     Davidson
    0.34
     Ім
    0.34
    ṇ
    0.34
     Hiroshima
    0.34
    MovieModal
    0.34
    POSITIVE LOGITS
    нды
    0.45
     given
    0.44
    gers
    0.38
    given
    0.37
    asers
    0.37
    fbox
    0.37
    给定
    0.36
    ไฟล์
    0.36
    宝
    0.36
    டுதல்
    0.35
    Activations Density 0.000%

    No Known Activations